© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84199
    Prev
    Next
    INDEX
    Explanations

    specific names, titles, and references related to academic or scientific entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ж
    -0.10
    rew
    -0.09
    iversit
    -0.08
    raw
    -0.08
    inner
    -0.08
    stå
    -0.07
    irma
    -0.07
    own
    -0.07
    amage
    -0.07
    AKE
    -0.07
    POSITIVE LOGITS
    ughter
    0.09
    urnal
    0.09
    ãģªãģĦ
    0.09
    rell
    0.08
    artment
    0.08
    initely
    0.08
    shire
    0.08
    .parseDouble
    0.08
    IALOG
    0.07
    ãģªãģı
    0.07
    Activations Density 2.513%

    No Known Activations